{"id":"W2039140614","doi":"10.1139/x03-230","title":"An evaluation of diagnostic tests and their roles in validating forest biometric models","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Forest ecology and management","field":"Environmental Science","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sign test; Wilcoxon signed-rank test; Test (biology); Statistics; Nonparametric statistics; Biometrics; Statistical hypothesis testing; Parametric statistics; Benchmark (surveying); Credibility; Computer science; Mathematics; Econometrics; Artificial intelligence; Mann–Whitney U test","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1215835,0.001950349,0.001535393,0.006223569,0.001341361,0.002912264,0.002648743,0.00224073,0.001464702],"category_scores_gemma":[0.3633519,0.0006111253,0.002132983,0.003654094,0.002258612,0.004809757,0.002289,0.00196057,0.0004121825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00229192,"about_ca_system_score_gemma":0.002705527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005148882,"about_ca_topic_score_gemma":0.005241601,"domain_scores_codex":[0.9274601,0.0519657,0.004420824,0.003708054,0.01160747,0.0008378235],"domain_scores_gemma":[0.4326802,0.5141125,0.01559908,0.01356645,0.02281351,0.001228199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001958485,0.0006714441,0.2471883,0.002009281,0.001100776,0.0005711681,0.00141202,0.2231574,0.007525796,0.03818556,0.004651656,0.4715681],"study_design_scores_gemma":[0.0002077458,0.002844014,0.05499721,0.0007642157,0.0004954102,0.00103454,0.00131094,0.8844442,0.01512377,0.03121512,0.007226099,0.0003367384],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2521178,0.003150538,0.7316774,0.001171855,0.000330335,0.000549577,0.001171434,0.00151039,0.008320789],"genre_scores_gemma":[0.6988195,0.0005685472,0.2987775,0.0001466188,0.00006721544,0.0002361384,0.0007679104,0.000138116,0.0004784385],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1215835,"threshold_uncertainty_score":0.6430025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.074468337547369,"score_gpt":0.336717009409145,"score_spread":0.2622486718617759,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}